DreamNLP: Novel NLP System for Clinical Report Metadata Extraction using Count Sketch Data Streaming Algorithm: Preliminary Results
This work addresses the problem of scalable information extraction from clinical reports for healthcare professionals, but it appears incremental as it adapts an existing algorithm to a specific domain.
The authors tackled the challenge of efficiently extracting metadata from electronic health records by proposing DreamNLP, a novel system based on a modified Count Sketch data streaming algorithm, which generated a dictionary of frequently occurring terms with low computational memory and demonstrated extraction of key breast diagnosis features from patient imaging data.
Extracting information from electronic health records (EHR) is a challenging task since it requires prior knowledge of the reports and some natural language processing algorithm (NLP). With the growing number of EHR implementations, such knowledge is increasingly challenging to obtain in an efficient manner. We address this challenge by proposing a novel methodology to analyze large sets of EHRs using a modified Count Sketch data streaming algorithm termed DreamNLP. By using DreamNLP, we generate a dictionary of frequently occurring terms or heavy hitters in the EHRs using low computational memory compared to conventional counting approach other NLP programs use. We demonstrate the extraction of the most important breast diagnosis features from the EHRs in a set of patients that underwent breast imaging. Based on the analysis, extraction of these terms would be useful for defining important features for downstream tasks such as machine learning for precision medicine.